Machine learning in point-of-care automated classification of oral potentially malignant and malignant disorders: a systematic review and meta-analysis

Abstract

Machine learning (ML) algorithms are becoming increasingly pervasive in the domains of medical diagnostics and prognostication, afforded by complex deep learning architectures that overcome the limitations of manual feature extraction. In this systematic review and meta-analysis, we provide an update on current progress of ML algorithms in point-of-care (POC) automated diagnostic classification systems for lesions of the oral cavity. Studies reporting performance metrics on ML algorithms used in automatic classification of oral regions of interest were identified and screened by 2 independent reviewers from 4 databases. Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. 35 studies were suitable for qualitative synthesis, and 31 for quantitative analysis. Outcomes were assessed using a bivariate random-effects model following an assessment of bias and heterogeneity. 4 distinct methodologies were identified for POC diagnosis: (1) clinical photography; (2) optical imaging; (3) thermal imaging; (4) analysis of volatile organic compounds. Estimated AUROC across all studies was 0.935, and no difference in performance was identified between methodologies. We discuss the various classical and modern approaches to ML employed within identified studies, and highlight issues that will need to be addressed for implementation of automated classification systems in screening and early detection.

Applying Machine Learning for Enhanced MicroRNA Analysis: A Companion Risk Tool for Oral Squamous Cell Carcinoma in Standard Care Incisional Biopsy

“…While conventional histopathology categorized this lesion with mild dysplasia as low risk, these molecular changes might indicate early changes not apparent histopathologically. It may well be that molecular analyses provide a complimentary understanding of changes occurring within tissues and align with recent studies [26] emphasizing the synergistic value of combining machine learning with traditional histopathological methods.…”

The implications of nanodiagnostics and artificial intelligence for detecting oral potentially malignant disorders and oral squamous cell carcinoma

“…As mentioned in two correspondence papers 1 , 2 , convolutional neural network is one such method of automated machine earning to diagnose oral cancer 13 , 14 . In fact, the issue on AI-assisted diagnosis of OPMD/OSCC was also well reviewed by earlier systematic reviews and meta-analyses 15 – 17 . AI-assisted diagnostic modalities in detecting OPMD/OSCC mainly contain photographic images, fluorescence spectroscopy, Raman spectroscopy, and OCT. Ferro et al 15 estimated the overall AUC across all the 35 studies was 0.935 for automated classification of oral cavity lesions.…”

“…In fact, the issue on AI-assisted diagnosis of OPMD/OSCC was also well reviewed by earlier systematic reviews and meta-analyses 15 – 17 . AI-assisted diagnostic modalities in detecting OPMD/OSCC mainly contain photographic images, fluorescence spectroscopy, Raman spectroscopy, and OCT. Ferro et al 15 estimated the overall AUC across all the 35 studies was 0.935 for automated classification of oral cavity lesions. Elmakaty et al 16 pooled the sensitivity and specificity with 95% CI being 92.0% (86.7–95.4%) and 91.9% (86.5–95.3%), respectively, across 16 studies on AI-assisted technologies in detecting OSCC.…”